INDEX

Explanations

physical descriptions

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ä¸Ńåįİäººæ°ĳ

-0.27

bsites

-0.27

 judgement

-0.26

å¿¤

-0.26

venth

-0.26

cip

-0.26

 Mime

-0.26

 handshake

-0.25

å¿ħ

-0.25

(Optional

-0.25

POSITIVE LOGITS

 Industry

0.28

Small

0.27

Reviewed

0.27

Rel

0.27

Rel

0.26

 Compact

0.26

 Small

0.25

 compact

0.25

 Computing

0.25

 industry

0.25

Activations Density 0.018%

physical descriptions

No Comments

No Known Activations